© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52031
    Prev
    Next
    INDEX
    Explanations

    user associated words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±ĭåŃIJ
    -0.10
    è¿Ļä¹Łæĺ¯
    -0.10
    UserRole
    -0.10
    ä¸įéĢļ
    -0.09
    æ¯ıä½į
    -0.09
    ä¸ŃåĽ½åĽ½éĻħ
    -0.09
    UserProfile
    -0.09
    人èĦī
    -0.09
    anja
    -0.09
    /she
    -0.09
    POSITIVE LOGITS
    fully
    0.12
    itarian
    0.12
    fulness
    0.11
    DEFINED
    0.11
    ful
    0.10
    innen
    0.10
    hood
    0.10
    èle
    0.10
    names
    0.09
    hip
    0.09
    Activations Density 0.095%

    No Known Activations